Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add coroboros/agent-skills --skill suno-producegit clone --depth 1 https://github.com/coroboros/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/coroboros/agent-skills/suno-produce)<a href="https://agentmods.dev/skills/coroboros/agent-skills/suno-produce"><img src="https://agentmods.dev/badge/skills/coroboros/agent-skills/suno-produce/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/coroboros/agent-skills/suno-produce"><img src="https://agentmods.dev/badge/skills/coroboros/agent-skills/suno-produce.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.04545 |
| Opus 5 | $0.00038 | $0.02273 |
| Sonnet 5 | $0.00015 | $0.00909 |
| Haiku 4.5 | $0.00008 | $0.00455 |
Grade A, and why
suno-produce scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suno Produce
Important — Writing rules
Apply these rules to emitted prose: docs, comments, commit messages, PR bodies, and release notes.
- Match surrounding punctuation, capitalization, and formatting.
- Every sentence changes the reader's understanding. Cut it otherwise.
- Lead with the action or outcome.
- Use concrete language and lists when they improve comparison or sequence.
- Assert positively. Reserve negation for real constraints (
NEVER commit secrets). - No marketing words: powerful, robust, seamlessly, leverage, unlock, comprehensive, delightful.
- No AI tells: delve, tapestry, intricate, pivotal, testament, underscore, crucial, garner, showcase, additionally, moreover, furthermore, indeed.
- For substantive English prose, use
/humanize-enif installed with the existing scope and authorization. It adds no approval stage; skip redundant passes over short status text.
Govern music-production artifacts for Suno v5.5: a TRACK.md per generation, optional ALBUM.md for multi-track projects, optional ARTIST.md for an artist-scoped identity layer. Three layers, each with a clear job. The user copy-pastes the Suno prompt block from TRACK.md into Suno's Web/iOS/Android UI, listens to the two takes Suno produces, picks a winner, then runs revise with feedback to iterate.
Artifact-emit-only by design. Suno has no official public API. Reverse-engineered wrappers (kie.ai, sunoapi.org, gcui-art/suno-api) are degrading — PiAPI dropped Suno V5 entirely, gcui-art's maintainer is asking for a takeover, the Warner Music settlement signals tighter enforcement. The text prompts are durable; they survive model deprecation. The audio takes are not — export WAV stems from Suno's UI for anything you want to keep.
Tier reality. v5.5 is Pro/Premier only. Free tier is locked to v4.5-all and stays non-commercial regardless of later upgrades. Validator and refs assume v5.5; running the prompts on v4.5-all degrades but does not crash.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 3.7 KB
- references/genre-templates.md 9.7 KB
- references/rights-and-deprecation.md 7.6 KB
- references/sliders-and-personalization.md 9.2 KB
- references/songwriting-craft.md 5.3 KB
- references/style-and-lyrics.md 19 KB
- references/track-schema.md 15 KB
- scripts/validate.py 37 KB runs code
- steps/create.md 11 KB
- steps/revise.md 7.5 KB
- steps/validate.md 6.1 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · -8 lines · -71 tokens per session 1435be9c8d2c
- 11d ago First seen · 177 lines · 147 tokens per session scan A 6e7588af5bda
suno-produce is a skill published in the GitHub repository coroboros/agent-skills (4 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 4,545 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hive.image-generation
Required before calling imagegenerate. Create and edit images from a prompt — generate an image, make a picture / logo / illustration / icon / banner / poster / thumbnail / hero image / mockup / product shot / social graphic, or edit / restyle / combine existing images from reference images. Uses OpenAI gpt-image-2…
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
art-director
AI art direction system. Claude directs image generation models (Gemini, DALL-E, Flux) via structured prompts. Generate banners, diagrams, logos, screenshots, and social media visuals without leaving the terminal.
agent-tamagotchi
Terminal pet that lives in your statusline. 12 species, 5 stats (DEBUGGING, PATIENCE, CHAOS, WISDOM, SPEED). Reacts to your workflow - happy when tests pass, sad when builds fail, excited during swarm mode. Deterministic species from user ID.
product-showcase
Generate a comprehensive marketing website for a web app — multi-page with real screenshots, animated GIF walkthroughs, feature deep-dives, and workflow demonstrations. Browses the running app, captures screens and sequences, and produces a deployable site that actually teaches people what the product does. Especially…
audio-production
Professional audio production for music, podcasts, and sound design. Use when working with audio recording, mixing, mastering, or sound design for any medium.